GPT Image 2.5 Sunburst: Text to Image
GPT Image 2.5 Sunburst is a high-fidelity image editing and generation template for creating polished, detail-rich visuals. It preserves subject identity, complex materials, lighting consistency and scene structure across iterations. Suitable for concept refinement, product visuals, character scenes, cinematic backgrounds and finished artwork that requires precision, realism and visual depth.
概要
GPT Image 2.5 Sunburst: Text to Image is a focused ComfyUI template that turns carefully structured prompts into polished, detail-rich images using OpenAI’s image generation API. The core of the workflow is OpenAIGPTImageNodeV2, which packages your prompt (using a "Sunburst" structure that calls out subject, materials, lighting, camera, and composition) and sends it to the selected OpenAI image model. The resulting image stream is then handed to SaveImage, which writes the outputs to your ComfyUI output directory.
入力するもの
- ワークフローを読み込み中
ComfyUI で実行できます。 このワークフローはこのページでは実行できません。すべてが読み込まれた状態でComfy Cloudで開くか、ご自身のComfyUI用にダウンロードしてください。
Cloudで試すよくある質問
It uses OpenAIGPTImageNodeV2 to call OpenAI’s image generation API. You can select the model inside the node (e.g., an available OpenAI image model on your account). The node also exposes typical options like size/aspect, quality/style, and number of outputs.
Repeat the same Sunburst anchor details every time (subject traits, materials, key props, lighting, lens/camera, and composition), and keep node parameters (model, size/aspect, quality) unchanged. OpenAI image models are non-deterministic, so exact pixel matches aren’t guaranteed, but stable anchors greatly improve identity and material consistency.
SaveImage writes files to your ComfyUI output directory. You can set a custom subfolder or filename prefix directly in the SaveImage node to organize outputs per project or prompt.
No. OpenAIGPTImageNodeV2 sends requests to OpenAI’s servers, so you need an active internet connection and a valid OpenAI API key. Usage is billed by your OpenAI account based on the model and settings you choose.